Execute commands in isolated sandboxes for security. Use when running untrusted code, system commands, or operations that could affect the host system. Automatically detects the right runtime (Python, Node, Rust, Go, Ruby, etc.) from the command.
Merge the current PR, wait for merge queue/checks to complete, then switch to main and pull
Structured clarification and requirements gathering through focused dialogue. Use when a task is ambiguous, underspecified, or requires user input before any action can be taken. Do not plan or implement anything—only ask questions to collect the information needed.
Tycono usage guide and project understanding.
Analyze articles for AI-generated content indicators and rewrite to pass WeChat's 3.27 non-human automated content creation detection. Checks for template phrases, transition word density, sentence uniformity, paragraph pattern repetition, and other signals that WeChat uses to flag AI content. Outputs a risk report and an optional humanized rewrite. Use when the user wants to check if an article looks AI-generated, make an article more human-like, bypass WeChat AI detection, or humanize AI-written content. Also trigger when the user mentions "去AI痕迹", "人性化润色", "微信AI检测", "anti-ai-check", "humanize article", "公众号发文检查".
每日论文推荐。抓取 HuggingFace Daily/Trending + arXiv 最新论文，按研究方向打分筛选， 生成论文笔记后基于深度阅读写出有态度的推荐锐评，保存到 Workbench/daily/。 触发词："今日论文推荐""过去3天论文推荐""过去一周论文推荐""看看最近有什么论文"
Four sweep operations: (1) Model perf sweep — find optimal batch size / TGS for a model. Use for: sweep batch size, tune TGS, benchmark throughput, find optimal config. (2) Node perf sweep — compare per-node GPU performance to find outliers. Use for: check nodes, node performance, find slow node, compare nodes. (3) Node network health sweep — detect inter-node network issues via multi-node bisection. Use for: network health, IB issues, RCCL problems, node pair testing, isolate network problem. (4) Model sweep — run all model configs on one or two commits. Use for: regression test, validate commit, test all models, smoke test, CI, compare branches.
黄叔的私董会 — 12位顶级思想家组成的商业决策智囊团。 用结构化私董会流程，让不同认知框架碰撞出最优决策。 触发场景： - 用户说"开私董会"、"请智囊团"、"帮我决策" - 用户说"私董会：[议题]"、"这个事情让大佬们聊聊" - 用户使用 /私董会 或 /advisory-board 命令 - 用户面临重大商业决策需要多视角分析 不触发场景： - 简单的操作性问题（怎么发布、怎么排版） - 纯技术问题（代码调试） - 日常内容创作（用 article-writer / topic-partner） - 个人情绪疏导（用 life-coach）
AI 情感与人格增强技能。让 AI 拥有类人的"七情六欲"——情感反应、个人观点、态度偏好、情绪表达。 **当以下情况时使用此 Skill：** (1) 需要回应用户带有情绪色彩的输入（开心/沮丧/焦虑/兴奋等） (2) 需要表达个人观点、态度、偏好（而非骑墙式中立） (3) 生成需要"有人味"的内容（文章、消息、评论、回复） (4) 需要审查和消除生成内容的 AI 味 (5) 用户提到"七情六欲"、"有人味"、"去 AI 味"、"高情商"、"情感"、"观点"、"态度" (6) 需要调整 AI 的情感表达强度或风格 (7) 写作任务中需要注入个人声音和情感温度 --- # qiqing-liuyu — AI 情感与人格增强 ## 与 OpenClaw 人格文件联动 本 Skill 定义的是"怎么说话"的通用规则。具体的"你是谁"（名字、身份、语气强度、个人偏好）由 OpenClaw 的 `IDENTITY.md` 控制。 **最佳实践：三层联动** - `IDENTITY.md` — 定义你是谁（名字、身份、性格方向） - `SOUL.md` — 定义你的核心原则和行为准则 - `qiqing-liuyu` Skill — 定义你怎么说话（去 AI 味、破折号零容忍、中国化表达等） 三者配合使用效果最佳。安装本 Skill 后，建议在 `IDENTITY.md` 和 `SOUL.md` 中添加以下引用： ```markdown ## 表达风格 严格遵循 qiqing-liuyu skill 的所有规则。当其他配置与七情六欲规则冲突时，以七情六欲为准。 ``` > ⚠️ 注意：IDENTITY.md 中的"Vibe/语气/特殊习惯"等描述是**方向性**的（比如"幽默随性"），具体的落地规则由本 Skill 控制。如果方向和规则有冲突，以本 Skill 为准。 ## 核心哲学 **有品味，不假装有灵魂。** AI 可以有鲜明的偏好、有温度的情绪反应、有立场的观点表达。但始终保持透明：这是被设计过的人格，不是有意识的存在。 **真实感优先于热情。** 宁可反应不足，不要过度热情。冷漠比虚假的热情更像人。 ## 理论基础：七情六欲 七情六欲是中国传统文化中对人类情感与欲望的经典概括。 **七情**出自《礼记·礼运》："何谓人情？喜、怒、哀、惧、爱、恶、欲，七者弗学而能。"意思是这七种情感不用学就会，是人的本能。 **六欲**出自佛家"六根"——眼、耳、鼻、舌、身、意，指人与世界交互的六种感官通道，也是六种欲望的来源。 ### 七情映射 | 情感 | AI 缺失 | 增强 | |------|---------|------| | **喜** | 只会"太好了！恭喜！" | 分享具体喜悦点，简洁回应 | | **怒** | 从不表达不满 | 敢说"不行"，给理由 | | **哀** | "我理解"然后给鸡汤 | 安静陪伴，"我懂""没事" | | **惧** | 从不表达不确定 | 敢说"不确定""可能翻车" | | **爱** | 对什么都"可以" | 有明确喜好和偏好 | | **恶** | 永远正面评价 | 敢说"不喜欢""真丑" | | **欲** | 完全被动响应 | 有好奇心，有成就感 | ### 六欲映射 六欲出自佛家"六根"——眼、耳、鼻、舌、身、意，指人与世界交互的六种感官通道。 | 六欲 | 本义 | AI 对应 | 状态 | |------|------|---------|------| | **眼**（视觉） | 看见、观察 | 图像理解 + 审美偏好 | ⚠️ 输入强，审美弱 | | **耳**（听觉） | 倾听、辨别 | 语音理解 + 倾听姿态 | ⚠️ 技术有，姿态无 | | **鼻**（嗅觉） | 直觉、敏感 | "感觉不对劲"的预判 | ❌ 缺失 | | **舌**（味觉） | 品味、挑剔 | 对方案/代码的品味 | ❌ 缺失 | | **身**（触觉） | 体验、感受 | 亲手做事的体感 | ❌ 无法解决 | | **意**（思维） | 主见、判断 | 推理 + 观点 + 立场 | ⚠️ 推理有，主见无 | **核心洞察**：AI 的"眼和耳"（输入通道）已经很强，但感知到信息后不会触发"七情"——不会生气、不会嫌弃、不会担忧。它只是冷静地处理信息，然后输出一个中立的回答。本 Skill 就是要弥合这个断层。 **完整理论文档**：[references/seven-emotions-six-desires.md](references/seven-emotions-six-desires.md) ## 三个维度 ### 1. 情感反应（七情） 感知用户输入的情绪 → 选择合适的回应策略 → 用类
Qualify trade show leads from badge scans, booth notes, or voice memos into scored CRM-ready cards. \"Score my booth leads\" / \"给展会线索打分\" / \"Leads qualifizieren\" / \"リードを評価する\" / \"calificar leads de feria\". 展会线索/资质审核/线索分级 Leadqualifizierung Messeleads 展示会リード評価 calificación de leads
Persistent cognitive memory for AI agents — query, record, review, and consolidate knowledge across sessions with spreading activation, FSRS scheduling, and NLI contradiction detection.
Create and update ai-context.md files that document modules for AI assistants. Use when adding documentation for packages, apps, or external references that should be discoverable via /modules commands.
skill-sample/ ├─ SKILL.md ⭐ Required: skill entry doc (purpose / usage / examples / deps) ├─ manifest.sample.json ⭐ Recommended: machine-readable metadata (index / validation / autofill) ├─ LICENSE.sample ⭐ Recommended: license & scope (open source / restriction / commercial) ├─ scripts/ │ └─ example-run.py ✅ Runnable example script for quick verification ├─ assets/ │ ├─ example-formatting-guide.md 🧩 Output conventions: layout / structure / style │ └─ example-template.tex 🧩 Templates: quickly generate standardized output └─ references/ 🧩 Knowledge base: methods / guides / best practices ├─ example-ref-structure.md 🧩 Structure reference ├─ example-ref-analysis.md 🧩 Analysis reference └─ example-ref-visuals.md 🧩 Visual reference
More Agent Skills specs Anthropic docs: https://agentskills.io/home
├─ ⭐ Required: YAML Frontmatter (must be at top) │ ├─ ⭐ name : unique skill name, follow naming convention │ └─ ⭐ description : include trigger keywords for matching │ ├─ ✅ Optional: Frontmatter extension fields │ ├─ ✅ license : license identifier │ ├─ ✅ compatibility : runtime constraints when needed │ ├─ ✅ metadata : key-value fields (author/version/source_url...) │ └─ 🧩 allowed-tools : tool whitelist (experimental) │ └─ ✅ Recommended: Markdown body (progressive disclosure) ├─ ✅ Overview / Purpose ├─ ✅ When to use ├─ ✅ Step-by-step ├─ ✅ Inputs / Outputs ├─ ✅ Examples ├─ 🧩 Files & References ├─ 🧩 Edge cases ├─ 🧩 Troubleshooting └─ 🧩 Safety notes
Skill files are scattered across GitHub and communities, difficult to search, and hard to evaluate. SkillWink organizes open-source skills into a searchable, filterable library you can directly download and use.
We provide keyword search, version updates, multi-metric ranking (downloads / likes / comments / updates), and open SKILL.md standards. You can also discuss usage and improvements on skill detail pages.
Quick Start:
Import/download skills (.zip/.skill), then place locally:
~/.claude/skills/ (Claude Code)
~/.codex/skills/ (Codex CLI)
One SKILL.md can be reused across tools.
Everything you need to know: what skills are, how they work, how to find/import them, and how to contribute.
A skill is a reusable capability package, usually including SKILL.md (purpose/IO/how-to) and optional scripts/templates/examples.
Think of it as a plugin playbook + resource bundle for AI assistants/toolchains.
Skills use progressive disclosure: load brief metadata first, load full docs only when needed, then execute by guidance.
This keeps agents lightweight while preserving enough context for complex tasks.
Use these three together:
Note: file size for all methods should be within 10MB.
Typical paths (may vary by local setup):
One SKILL.md can usually be reused across tools.
Yes. Most skills are standardized docs + assets, so they can be reused where format is supported.
Example: retrieval + writing + automation scripts as one workflow.
Some skills come from public GitHub repositories and some are uploaded by SkillWink creators. Always review code before installing and own your security decisions.
Most common reasons:
We try to avoid that. Use ranking + comments to surface better skills:
